Model card for efficientnet b1.ra4 e3600 r240 in1k A EfficientNet image classification model. Trained on ImageNet 1k by Ross Wightman. Trained with timm scripts using hyper parameters inspired by the MobileNet V4 small, mixed with go to hparams from timm and "ResNet Strikes Back". A collection of hparams (timm .yaml config files) for this training series can be found here: https://gist.github.com/rwightman/f6705cb65c03daeebca8aa129b1b94ad Model Details Model Type: Image classification / feature backbone Model Stats: Params (M): 7.8 GMACs: 0.7 Activations (M): 10.9 Image size: train = 240 x 240, test = 288 x 288 Dataset: ImageNet 1k Papers: PyTorch Image Models: https://github.com/huggingface/pytorch image models EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 MobileNetV4 Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518 Model Usage Image Classification Feature Map Extraction Image Embeddings Model Comparison By Top 1 model top1 top5 param count img size mobilenetv4 conv aa large.e230 r448 in12k ft in1k 84.99 97.294 32.59 544 mobilenetv4 conv aa large.e230 r384 in12k ft in1k 84.772 97.344 32.59 480…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy